Acute lymphoblastic leukemia is the most common cancer in children, and its diagnosis mainly includes microscopic blood tests of the bone marrow. Therefore, there is a need for a correct classification of white blood cells. The approach developed in this article is based on an optimized and small IoT-friendly neural network architecture. The application of learning transfer in hybrid artificial intelligence systems is offered. The hybrid system consisted of a MobileNet v2 encoder pre-trained on the ImageNet dataset and machine learning algorithms performing the role of the head. These were the XGBoost, Random Forest, and Decision Tree algorithms. In this work, the average accuracy was over 90%, reaching 97.4%. This work proves that using hybrid artificial intelligence systems for tasks with a low computational complexity of the processing units demonstrates a high classification accuracy. The methods used in this study, confirmed by the promising results, can be an effective tool in diagnosing other blood diseases, facilitating the work of a network of medical institutions to carry out the correct treatment schedule.

Digital image correlation may be useful in many different fields of science, one of which is medicine. In this paper, the authors present the results of research aimed at detecting skin micro-shifts caused by pulsation of the veins. A novel technique using digital image correlation (DIC) and filtering the resulting shifts map to detect pulsating veins was proposed. After applying the proposed method, the veins in the forearm were visualized. The proposed technique may be used in the diagnosis of venous stenosis and may also contribute to reducing the number of adverse events during blood collection. The great advantage of the proposed method is the lack of the need to have specialized equipment, only a typical mobile phone camera is needed to perform the test.

In this study, molecular dynamics simulations were employed to analyze interactions between phospholipid membranes and human serum albumin (HSA) in the presence of mono- and divalent cations. Two types of membranes, composed of dipalmitoyl phosphatidylcholine (DPPC) and dipalmitoyl phosphatidylethanolamine (DPPE), were utilized. The results revealed that both systems exhibited high stability. The DPPE complexes displayed a greater affinity for albumin compared to DPPC. The high stability of the complexes was attributed to a high number of ionic contacts and hydrogen bonds. The presence of mono- and divalent metal cations significantly influenced the membrane’s capacity to bind proteins. However, these effects varied depending on the phospholipid composition of the bilayer. The studies confirmed the relatively low ability of DPPC to bind potassium ions, as previously observed by others. Consequently, the DPPC/HSA/K⁺ complex was found to be the least stable among the systems studied. While DPPC interactions were limited to HSA domains I and II, DPPE was able to interact with all domains of the protein. Both lipid bilayers exhibited substantial structural changes and characteristic curvature induced by interactions with HSA, which confirms the formation of relatively strong interactions capable of influencing the arrangement of the phospholipids.

This paper discusses an evaluation method of transmission properties of networks described with regular graphs (Reference Graphs) using unevenness coefficients. The first part of the paper offers generic information about describing network topology via graphs. The terms ‘chord graph’ and ‘Reference Graph’, which is a special form of a regular graph, are defined. The operating principle of a basic tool used for testing the network’s transmission properties is discussed. The next part consists of a description of the searching procedure of the shortest paths connecting any two nodes of a graph and the method determining the number of uses of individual graph edges. The analysis shows that using particular edges of a graph depends on two factors: their total number in minimum length paths and their total number in parallel paths connecting the graph nodes. The latter makes it possible to define an unevenness coefficient. The calculated values of the unevenness coefficients can be used to evaluate the transmission properties of networks and to control the distribution of transmission resources.

The paper discusses the method of improvement of transmission properties of ICT networks by setting the correct distribution of transmission resources in order that it is possible to increase the resulting global probability of supporting the calls generated in the nodes included in the network. The method uses some parts of the graph theory. A minimum length path searching algorithm was used which made it possible to calculate the volume of movement transferred by individual edges of the graph describing the network. The coefficient of the distribution of transmission resources was determined and used to calculate the value of the resources in reference to a particular link, both in the case of equal and diverse movement generated in individual network nodes. A piece of software was developed which uses the results of applying the above-mentioned algorithm to prepare the files describing the analyzed structures in order to carry out simulation tests. The views and analyses are illustrated by examples, and the resulting effects of the influence of the introduction of the method of dividing network resources into transmission properties of a network modelled by graphs are shown in the charts included.